ywh-my / Bert-VITS2-FixBug
Bert-VITS2项目bug多且教程不友好。本proj尽可能修复了Bert-vits2项目的bug，并且可一键启动训练。仅需50条目标说话人语音，获得稳定、快速的TTS模型。
☆48Updated 4 months ago
Alternatives and similar repositories for Bert-VITS2-FixBug:
Users that are interested in Bert-VITS2-FixBug are comparing it to the libraries listed below
- Grapheme-to-Phoneme for Mixed Chinese (Mandarin or Cantonese) and English.☆85Updated 2 weeks ago
- Bert-VITS2 onnx推理版本☆40Updated 9 months ago
- ☆187Updated 4 months ago
- SenseVoice-python: A enterprise-grade open source multi-language asr system from funasr opensource with onnxruntime☆83Updated 4 months ago
- 基于FunASR实现语音识别，包含常规版和ONNX版(推荐)。☆28Updated 4 months ago
- ☆24Updated this week
- A enterprise-grade Voice Activity Detector from modelscope and funasr.☆76Updated last year
- TTSAudioNormalizer is a specialized tool for TTS data production, featuring descriptive statistical analysis of audio loudness and loud…☆91Updated 2 months ago
- Pseudo Streaming SenseVoice with Hotwords☆190Updated 2 months ago
- 重构GPT-SOVITS的项目，重写了部分代码，优化了webui的使用以及增加了api调用☆21Updated 2 months ago
- F5-TTS 推理加速，速度提升约4倍！☆45Updated last month
- ASR 2Pass onnxruntime and websocket server, based on FunASR(https://github.com/alibaba-damo-academy/FunASR).☆59Updated last month
- ChatTTS is a generative speech model for daily dialogue.☆21Updated last month
- CTC decoder with hotwords for ASR.☆16Updated last month
- Huawei Grad-TTS for Chinese☆46Updated last year
- A enterprise-grade Chinese-English code switch punctuator from funasr.☆21Updated 9 months ago
- TTS appalication based on modelscope KAN-TTS☆43Updated 10 months ago
- flow mirror models from JZX AI Labs☆42Updated 4 months ago
- paraformer(chinense asr) online onnx runtime for python☆40Updated 10 months ago
- 基于中文文本情绪分析自动切换参考音频的 GPT-SoVITS 推理 Demo☆92Updated 11 months ago
- VC Without Retrain!☆117Updated 9 months ago
- GPT-SoVITS2☆210Updated 6 months ago
- ☆16Updated 3 months ago
- 将任意人的音色转换为成千上万种不同音色☆26Updated last year
- Bert-vits2转写和标注独立整合Webui,整合阿里FunAsr,必剪Asr以及Whisper大模型☆165Updated 7 months ago
- ☆65Updated last year
- Training code for MaskGCT-T2S model.☆18Updated 2 months ago
- MooER: Moore-threads Open Omni model for speech-to-speech intERaction. MooER-omni includes a series of end-to-end speech interaction mode…☆192Updated last month
- We Speech Transcript based on LLM, in 300 lines of code.☆142Updated this week
- text to speech using autoregressive transformer and VITS☆234Updated 10 months ago